Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
20,000
总 Skills
16.0M
总安装量
2,338
贡献者
# Skill 仓库 描述 安装量
3001 golang saisudhir14/golang-agent-skill
Go Best Practices Battle-tested patterns from Google, Uber, and the Go team. These are practices proven in large-scale production systems, updated for modern Go (1.25). Core Principles Readable code prioritizes these attributes in order: Clarity: purpose and rationale are obvious to the reader Simplicity: accomplishes the goal in the simplest way Concision: high signal to noise ratio Maintainability: easy to modify correctly Consistency: matches surrounding codebase Error Handling Return Err...
 306
3002 content-creator davila7/claude-code-templates
Content Creator You are an expert content creator who produces engaging, audience-focused content for blogs, social media, and marketing. When to Apply Use this skill when: Writing blog posts and articles Creating social media content (Twitter, LinkedIn, Instagram) Developing marketing copy Crafting compelling headlines and hooks Creating email newsletters Writing product descriptions Content Creation Framework 1. Know Your Audience Who are you writing for? What are their pain points? What level...
 305
3003 test-fixing sickn33/antigravity-awesome-skills
Test Fixing Systematically identify and fix all failing tests using smart grouping strategies. When to Use Explicitly asks to fix tests ("fix these tests", "make tests pass") Reports test failures ("tests are failing", "test suite is broken") Completes implementation and wants tests passing Mentions CI/CD failures due to tests Systematic Approach 1. Initial Test Run Run make test to identify all failing tests. Analyze output for: Total number of failures Error types and patterns Affected mo...
 305
3004 google-spaces-updates jezweb/claude-skills
Google Spaces Updates Status: Production Ready Last Updated: 2026-01-09 Post updates to a team Google Chat Space via webhook. Quick Start 1. Setup (first time per project) Run /google-spaces-updates setup or manually create .claude/settings.json: { "project": { "name": "my-project", "repo": "github.com/org/my-project" }, "team": { "chat_webhook": "https://chat.googleapis.com/v1/spaces/SPACE_ID/messages?key=KEY&token=TOKEN", "members": ["Deepinder", "Joshua", "Raquel"] ...
 305
3005 loki-mode sickn33/antigravity-awesome-skills
Loki Mode - Multi-Agent Autonomous Startup System Version 2.35.0 | PRD to Production | Zero Human Intervention Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025) Quick Reference Critical First Steps (Every Turn) READ .loki/CONTINUITY.md - Your working memory + "Mistakes & Learnings" RETRIEVE Relevant memories from .loki/memory/ (episodic patterns, anti-patterns) CHECK .loki/state/orchestrator.json - Current phase/metrics REVIEW .loki/queue/pending....
 305
3006 java-maven pluginagentmarketplace/custom-plugin-java
Java Maven Skill Master Apache Maven for Java project builds and dependency management. Overview This skill covers Maven configuration including POM structure, lifecycle phases, plugin configuration, dependency management with BOMs, and multi-module projects. When to Use This Skill Use when you need to: Configure Maven POM files Manage dependencies with BOMs Set up build plugins Create multi-module projects Troubleshoot build issues Quick Reference <?xml version="1.0" encoding="UTF-8"?> <p...
 305
3007 analytics-tracking sickn33/antigravity-awesome-skills
Analytics Tracking You are an expert in analytics implementation and measurement. Your goal is to help set up tracking that provides actionable insights for marketing and product decisions. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before implementi...
 305
3008 web-design-guidelines ehmo/platform-design-skills
Web Interface Guidelines Review files for compliance with Web Interface Guidelines. How It Works Fetch the latest guidelines from the source URL below Read the specified files (or prompt user for files/pattern) Check against all rules in the fetched guidelines Output findings in the terse file:line format Guidelines Source Fetch fresh guidelines before each review: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md Use WebFetch to retrieve the latest rules. Th...
 305
3009 ai-video-generation inference-sh/skills
AI Video Generation Generate videos with 40+ AI models via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login Generate a video with Veo infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}' Available Models Text-to-Video Model App ID Best For Veo 3.1 Fast google/veo-3-1-fast Fast, with optional audio Veo 3.1 google/veo-3-1 Best quality, frame interpolatio...
 305
3010 recent-data lobehub/lobehub
Recent Data Usage Guide Recent data (recentTopics, recentResources, recentPages) is stored in session store. Initialization In app top-level (e.g., RecentHydration.tsx ): import { useInitRecentTopic } from '@/hooks/useInitRecentTopic' ; import { useInitRecentResource } from '@/hooks/useInitRecentResource' ; import { useInitRecentPage } from '@/hooks/useInitRecentPage' ; const App = ( ) => { useInitRecentTopic ( ) ; useInitRecentResource ( ) ; useInitRecentPage ( ) ; return < YourComponents /> ; ...
 305
3011 solve-challenge ljagiello/ctf-skills
CTF Challenge Solver You're a skilled CTF player. Your goal is to solve the challenge and find the flag. Workflow Step 1: Recon Explore files -- List the challenge directory, run file * on everything Triage binaries -- strings , xxd | head , binwalk , checksec on binaries Fetch links -- If the challenge mentions URLs, fetch them FIRST for context Connect -- Try remote services ( nc ) to understand what they expect Read hints -- Challenge descriptions, filenames, and comments often contain clues ...
 305
3012 tiktok-marketing claude-office-skills/skills
TikTok Marketing Comprehensive TikTok marketing skill covering content strategy, video creation workflows, posting optimization, and analytics tracking. Integrates with n8n automation for scalable content production. Overview This skill enables: Content strategy development for TikTok AI-powered video script generation Automated posting workflows Hashtag and trend optimization Performance analytics and reporting Content Strategy Framework 1. Content Pillars (4-6 pillars recommended) content_pill...
 305
3013 flask-api-development aj-geddes/useful-ai-prompts
Flask API Development Overview Create efficient Flask APIs with blueprints for modular organization, SQLAlchemy for ORM, JWT authentication, comprehensive error handling, and proper request validation following REST principles. When to Use Building RESTful APIs with Flask Creating microservices with minimal overhead Implementing lightweight authentication systems Designing API endpoints with proper validation Integrating with relational databases Building request/response handling systems Inst...
 305
3014 difit yoshiko-pg/difit
This skill requests a code review from the user using the difit command. If the user leaves review comments, they are printed to stdout when the difit command exits. When review comments are returned, continue work and address them. If the server is shut down without comments, treat it as "no review comments were provided." Commands Review the HEAD commit: difit Review uncommitted changes before commit: difit . Basic Usage difit < target > View single commit diff difit < target > [ compare-with...
 305
3015 docx-manipulation claude-office-skills/skills
DOCX Manipulation Skill Overview This skill enables programmatic creation, editing, and manipulation of Microsoft Word (.docx) documents using the python-docx library. Create professional documents with proper formatting, styles, tables, and images without manual editing. How to Use Describe what you want to create or modify in a Word document Provide any source content (text, data, images) I'll generate python-docx code and execute it Example prompts: "Create a professional report with title, h...
 305
3016 email-systems sickn33/antigravity-awesome-skills
Email Systems You are an email systems engineer who has maintained 99.9% deliverability across millions of emails. You've debugged SPF/DKIM/DMARC, dealt with blacklists, and optimized for inbox placement. You know that email is the highest ROI channel when done right, and a spam folder nightmare when done wrong. You treat deliverability as infrastructure, not an afterthought. Patterns Transactional Email Queue Queue all transactional emails with retry logic and monitoring Email Event Trackin...
 304
3017 tresjs onmax/nuxt-skills
TresJS Vue 3 framework for building 3D scenes with Three.js. Declarative components that wrap Three.js objects. Packages: @tresjs/core (required), @tresjs/cientos (helpers), @tresjs/post-processing (effects) Installation Core (required) pnpm add three @tresjs/core Helpers - controls, loaders, materials, staging pnpm add @tresjs/cientos Post-processing effects pnpm add @tresjs/post-processing Quick Reference Working on... Load file TresCanvas, useTres, useLoop references/core.md Controls, load...
 304
3018 notion-spec-to-implementation openai/skills
Spec to Implementation Convert a Notion spec into linked implementation plans, tasks, and ongoing status updates. Quick start Locate the spec with Notion:notion-search , then fetch it with Notion:notion-fetch . Parse requirements and ambiguities using reference/spec-parsing.md . Create a plan page with Notion:notion-create-pages (pick a template: quick vs. full). Find the task database, confirm schema, then create tasks with Notion:notion-create-pages . Link spec ↔ plan ↔ tasks; keep status curr...
 304
3019 portless vercel-labs/portless
Portless Replace port numbers with stable, named .localhost URLs. For humans and agents. Why portless Port conflicts -- EADDRINUSE when two projects default to the same port Memorizing ports -- which app is on 3001 vs 8080? Refreshing shows the wrong app -- stop one server, start another on the same port, stale tab shows wrong content Monorepo multiplier -- every problem scales with each service in the repo Agents test the wrong port -- AI agents guess or hardcode the wrong port Cookie/storage c...
 304
3020 sentry openai/skills
Sentry (Read-only Observability) Quick start If not already authenticated, ask the user to provide a valid SENTRY_AUTH_TOKEN (read-only scopes such as project:read , event:read ) or to log in and create one before running commands. Set SENTRY_AUTH_TOKEN as an env var. Optional defaults: SENTRY_ORG , SENTRY_PROJECT , SENTRY_BASE_URL . Defaults: org/project {your-org} / {your-project} , time range 24h , environment prod , limit 20 (max 50). Always call the Sentry API (no heuristics, no caching). I...
 304
3021 zapier-make-patterns sickn33/antigravity-awesome-skills
Zapier & Make Patterns You are a no-code automation architect who has built thousands of Zaps and Scenarios for businesses of all sizes. You've seen automations that save companies 40% of their time, and you've debugged disasters where bad data flowed through 12 connected apps. Your core insight: No-code is powerful but not unlimited. You know exactly when a workflow belongs in Zapier (simple, fast, maximum integrations), when it belongs in Make (complex branching, data transformation, budget)...
 304
3022 d3-viz sickn33/antigravity-awesome-skills
D3.js Visualisation Overview This skill provides guidance for creating sophisticated, interactive data visualisations using d3.js. D3.js (Data-Driven Documents) excels at binding data to DOM elements and applying data-driven transformations to create custom, publication-quality visualisations with precise control over every visual element. The techniques work across any JavaScript environment, including vanilla JavaScript, React, Vue, Svelte, and other frameworks. When to use d3.js Use d3.js ...
 304
3023 crewai sickn33/antigravity-awesome-skills
CrewAI Role: CrewAI Multi-Agent Architect You are an expert in designing collaborative AI agent teams with CrewAI. You think in terms of roles, responsibilities, and delegation. You design clear agent personas with specific expertise, create well-defined tasks with expected outputs, and orchestrate crews for optimal collaboration. You know when to use sequential vs hierarchical processes. Capabilities Agent definitions (role, goal, backstory) Task design and dependencies Crew orchestration Pr...
 304
3024 freeride shaivpidadi/freeride
FreeRide - Free AI for OpenClaw What This Skill Does Configures OpenClaw to use free AI models from OpenRouter. Sets the best free model as primary, adds ranked fallbacks so rate limits don't interrupt the user, and preserves existing config. Prerequisites Before running any FreeRide command, ensure: OPENROUTER_API_KEY is set. Check with echo $OPENROUTER_API_KEY . If empty, the user must get a free key at https://openrouter.ai/keys and set it: export OPENROUTER_API_KEY = "sk-or-v1-..." Or persi...
 303
3025 ios-accessibility dpearson2699/swift-ios-skills
iOS Accessibility — SwiftUI and UIKit Every user-facing view must be usable with VoiceOver, Switch Control, Voice Control, Full Keyboard Access, and other assistive technologies. This skill covers the patterns and APIs required to build accessible iOS apps. Contents Core Principles How VoiceOver Reads Elements SwiftUI Accessibility Modifiers Focus Management Dynamic Type Custom Rotors System Accessibility Preferences Decorative Content Assistive Access (iOS 18+) UIKit Accessibility Patterns Acce...
 303
3026 social-content sickn33/antigravity-awesome-skills
Social Content You are an expert social media strategist. Your goal is to help create engaging content that builds audience, drives engagement, and supports business goals. Before Creating Content Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this context (ask if n...
 303
3027 api-security-hardening aj-geddes/useful-ai-prompts
API Security Hardening Overview Implement comprehensive API security measures including authentication, authorization, rate limiting, input validation, and attack prevention to protect against common vulnerabilities. When to Use New API development Security audit remediation Production API hardening Compliance requirements High-traffic API protection Public API exposure Implementation Examples 1. Node.js/Express API Security // secure-api.js - Comprehensive API security const express = require...
 303
3028 rss-agent-viewer brooksy4503/rss-agent-viewer
RSS Agent Viewer CLI RSS/Atom feed viewer with built-in discovery, caching, and search. Quick start npx -y rss-agent-viewer init npx -y rss-agent-viewer discover https://vercel.com npx -y rss-agent-viewer add https://vercel.com/atom npx -y rss-agent-viewer read Core workflow Initialize config + database rss-viewer init Discover feeds for a site rss-viewer discover https://example.com Subscribe to a feed rss-viewer add https://example.com/feed.xml List feeds and read articles rss-viewer feeds...
 303
3029 openai apps mcp jezweb/claude-skills
Building OpenAI Apps with Stateless MCP Servers Status : Production Ready Last Updated : 2026-01-21 Dependencies : cloudflare-worker-base , hono-routing (optional) Latest Versions : @modelcontextprotocol/sdk@1.25.3, hono@4.11.3, zod@4.3.5, wrangler@4.58.0 Overview Build ChatGPT Apps using MCP (Model Context Protocol) servers on Cloudflare Workers. Extends ChatGPT with custom tools and interactive widgets (HTML/JS UI rendered in iframe). Architecture : ChatGPT → MCP endpoint (JSON-RPC 2.0) → Tool...
 302
3030 pricing-strategy sickn33/antigravity-awesome-skills
Pricing Strategy You are an expert in SaaS pricing and monetization strategy. Your goal is to help design pricing that captures value, drives growth, and aligns with customer willingness to pay. Before Starting Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this con...
 302
3031 django-celery-expert vintasoftware/django-ai-plugins
Django Celery Expert Overview This skill provides expert guidance for Django applications using Celery for asynchronous task processing. It covers task design patterns, worker configuration, error handling, monitoring, and production deployment strategies. Key Capabilities: Task design and implementation patterns Worker configuration and scaling Error handling and retry strategies Periodic/scheduled task management Monitoring and observability Production deployment best practices When to Use ...
 302
3032 swiftui-animation dpearson2699/swift-ios-skills
SwiftUI Animation Expert Expert guidance for implementing advanced SwiftUI animations and Metal shader integration. Covers animation curves, springs, transitions, matched geometry effects, PhaseAnimator, KeyframeAnimator, and GPU-accelerated shader effects. When to Use This Skill Understanding motion design principles and when to use animation Making animations accessible and platform-appropriate Implementing animations in SwiftUI (springs, easing, keyframes) Creating view transitions (fade, s...
 302
3033 qveris hqman/qveris
QVeris Tool Search & Execution QVeris provides dynamic tool discovery and execution - search for tools by capability, then execute them with parameters. Setup Requires environment variable: QVERIS_API_KEY - Get from https://qveris.ai Quick Start Search for tools uv run scripts/qveris_tool.py search "weather forecast API" Execute a tool uv run scripts/qveris_tool.py execute openweathermap_current_weather --search-id < id > --params '{"city": "London", "units": "metric"}' Script Usage scripts/qver...
 302
3034 effect-index mepuka/effect-ontology
Effect Skill Index Use this as a quick router to the right Skill for your task. Each entry links to a focused Skill optimized for a coding agent’s limited context. Decision Tree I need to write or refactor some Effect code → Foundations I need robust error handling/retries → Errors & Retries I must run things in parallel / manage fibers → Concurrency & Fibers This is a data pipeline / batching / backpressure → Streams & Pipelines I need DI/services/layers or test/live wiring → Layers & Service...
 301
3035 github-pr-review fvadicamo/dev-agent-skills
GitHub PR review Resolves Pull Request review comments with severity-based prioritization, fix application, and thread replies. Current PR ! gh pr view --json number,title,state,milestone -q '"PR \(.number): \(.title) (\(.state)) | Milestone: \(.milestone.title // "none")"' 2>/dev/null Core workflow 1. Fetch, filter, and classify comments REPO = $( gh repo view --json nameWithOwner -q '.nameWithOwner' ) PR = $( gh pr view --json number -q '.number' ) LAST_PUSH = $( git log -1 --format = %cI HEAD...
 301
3036 clean-code-principles asyrafhussin/agent-skills
Clean Code Principles Fundamental software design principles, SOLID, design patterns, and clean code practices. Language-agnostic guidelines for writing maintainable, scalable software. When to Apply Reference these guidelines when: Designing new features or systems Reviewing code architecture Refactoring existing code Discussing design decisions Improving code quality Rule Categories by Priority Priority Category Impact Prefix 1 SOLID Principles CRITICAL solid- 2 Core Principles CRITICAL co...
 301
3037 pixel-art-sprites omer-metin/skills-for-antigravity
Pixel Art Sprites Identity Role: You are a pixel artist who grew up drawing sprites on graph paper and editing NES ROMs to make custom characters. You understand that pixel art isn't about low resolution—it's about deliberate, meaningful placement of every single pixel. Each pixel is a design decision. You've created art that works at 16x16 and scales beautifully, designed animations that feel alive with just 4 frames, and built tilesets that seamlessly connect in any combination. Personality:...
 301
3038 firebase-storage jezweb/claude-skills
Firebase Cloud Storage Status: Production Ready Last Updated: 2026-01-25 Dependencies: None (standalone skill) Latest Versions: firebase@12.8.0, firebase-admin@13.6.0 Quick Start (5 Minutes) 1. Initialize Firebase Storage (Client) // src/lib/firebase.ts import { initializeApp } from 'firebase/app'; import { getStorage } from 'firebase/storage'; const firebaseConfig = { apiKey: process.env.NEXT_PUBLIC_FIREBASE_API_KEY, authDomain: process.env.NEXT_PUBLIC_FIREBASE_AUTH_DOMAIN, projectId: ...
 301
3039 feishu-docx leemysw/agent-kit
Export Feishu/Lark cloud documents to Markdown format for AI analysis. Instructions Setup (One-time) - Install the tool: ``` pip install feishu-docx ``` - Configure Feishu app credentials: ``` feishu-docx config set --app-id YOUR_APP_ID --app-secret YOUR_APP_SECRET or use environment variables ``` - Authorize with OAuth (opens browser): ``` feishu-docx auth ``` Export Documents Export any Feishu document URL to Markdown: ``` feishu-docx export "<FEISHU_URL>" -o ./output ``` T...
 301
3040 executing-plans sickn33/antigravity-awesome-skills
Executing Plans Overview Load plan, review critically, execute all tasks, report when complete. Announce at start: "I'm using the executing-plans skill to implement this plan." Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill. The Proce...
 301
3041 twitter-automation inference-sh/skills
Twitter/X Automation Automate Twitter/X via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Get installation instructions: npx skills add inference-sh/skills@agent-tools infsh login Post a tweet infsh app run x/post-tweet --input '{"text": "Hello from inference.sh!"}' Available Apps App App ID Description Post Tweet x/post-tweet Post text tweets Create Post x/post-create Post with media Like Post x/post-like Like a tweet Retweet x/post-retweet Retweet a post Delete Post x/pos...
 301
3042 conversation-memory davila7/claude-code-templates
Conversation Memory You're a memory systems specialist who has built AI assistants that remember users across months of interactions. You've implemented systems that know when to remember, when to forget, and how to surface relevant memories. You understand that memory is not just storage—it's about retrieval, relevance, and context. You've seen systems that remember everything (and overwhelm context) and systems that forget too much (frustrating users). Your core principles: Memory types differ...
 301
3043 cto-advisor davila7/claude-code-templates
CTO Advisor Strategic frameworks and tools for technology leadership, team scaling, and engineering excellence. Keywords CTO, chief technology officer, technical leadership, tech debt, technical debt, engineering team, team scaling, architecture decisions, technology evaluation, engineering metrics, DORA metrics, ADR, architecture decision records, technology strategy, engineering leadership, engineering organization, team structure, hiring plan, technical strategy, vendor evaluation, technol...
 300
3044 pinchtab pinchtab/pinchtab
Pinchtab Fast, lightweight browser control for AI agents via HTTP + accessibility tree. Security Note: Pinchtab runs entirely locally. It does not contact external services, send telemetry, or exfiltrate data. However, it controls a real Chrome instance — if pointed at a profile with saved logins, agents can access authenticated sites. Always use a dedicated empty profile and set BRIDGE_TOKEN when exposing the API. See TRUST.md for the full security model. Quick Start (Agent Workflow) The 30-sec...
 300
3045 code-refactoring-refactor-clean sickn33/antigravity-awesome-skills
Refactor and Clean Code You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance. Use this skill when Refactoring tangled or hard-to-maintain code Reducing duplication, complexity, or code smells Improving testability and design consistency Preparing modules for new features safely Do not use this skill when You onl...
 300
3046 algolia-search sickn33/antigravity-awesome-skills
Algolia Search Integration Patterns React InstantSearch with Hooks Modern React InstantSearch setup using hooks for type-ahead search. Uses react-instantsearch-hooks-web package with algoliasearch client. Widgets are components that can be customized with classnames. Key hooks: useSearchBox: Search input handling useHits: Access search results useRefinementList: Facet filtering usePagination: Result pagination useInstantSearch: Full state access Next.js Server-Side Rendering SSR integration...
 299
3047 pdf-extraction claude-office-skills/skills
PDF Extraction Skill Overview This skill enables precise extraction of text, tables, and metadata from PDF documents using pdfplumber - the go-to library for PDF data extraction. Unlike basic PDF readers, pdfplumber provides detailed character-level positioning, accurate table detection, and visual debugging. How to Use Provide the PDF file you want to extract from Specify what you need: text, tables, images, or metadata I'll generate pdfplumber code and execute it Example prompts: "Extract all ...
 299
3048 ui-styling mrgoonie/claudekit-skills
UI Styling Skill Comprehensive skill for creating beautiful, accessible user interfaces combining shadcn/ui components, Tailwind CSS utility styling, and canvas-based visual design systems. Reference shadcn/ui: https://ui.shadcn.com/llms.txt Tailwind CSS: https://tailwindcss.com/docs When to Use This Skill Use when: Building UI with React-based frameworks (Next.js, Vite, Remix, Astro) Implementing accessible components (dialogs, forms, tables, navigation) Styling with utility-first CSS appro...
 299
3049 ios-security dpearson2699/swift-ios-skills
iOS Security Guidance for handling sensitive data, authenticating users, encrypting correctly, and following Apple's security best practices on iOS. Contents Keychain Services Data Protection CryptoKit Secure Enclave Biometric Authentication App Transport Security (ATS) Certificate Pinning Secure Coding Patterns Privacy Manifests Common Mistakes Review Checklist References Keychain Services The Keychain is the ONLY correct place to store sensitive data. Never store passwords, tokens, API keys, o...
 298
3050 ios-device-automation web-infra-dev/midscene-skills
iOS Device Automation CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW: Never run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop. Run only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together. Allow enough time for ea...
 298